langchain 之 Tools 多案例使用（一）

ATTENTION:

  1. 如果采用 openai 的接口，需要走代理，本文采用 proxychains 进行设置。
  2. 开启 debug 模式后，能看到更多的输出信息。
import langchain
langchain.debug = True

1. Tools

参数如下。

  • name (str), 必填参数，并且在提供给代理的一组工具中必须是唯一的。
  • description (str), 可选参数，但推荐使用，因为它由代理用于确定工具的使用。描述的越清晰，LLM采用工具完成的任务越准确！
  • return_direct (bool), defaults to False
  • args_schema (Pydantic BaseModel), 可选参数，但推荐使用，可用于提供更多信息（例如，few-shot examples）或验证预期参数( validation for expected parameters)。
  • func (function), 必填，传入 tool 需要执行的操作。可以是 class、function等等。
  • coroutine (function), 可选参数，传入参数与 func 一样，但是需要用 async 修饰。

典型函数：

def read_previous_db(words:str)
      ....

class CInput(pydantic.BaseModel):
    question: str = pydantic.Field()

tool = Tool.from_function(func=read_previous_db,
                             name="previous_records",
                             description="用于回答与用户的历史对话信息，直接传入用户的问题，将查询后的结果再用 xx 工具回答给用户"
                              # args_schema=CInput,
                             )

1.1 调用自定义函数（局部代码）

如下面代码所示，可以通过接口使用 SQL 语句查询数据库

import requests
from typing import List, Dict, Any
import json

def vocab_lookup(
        search: str,
        entity_type: str = "item",
        url: str = "https://www.wikidata.org/w/api.php",
        user_agent_header: str = wikidata_user_agent_header,
        srqiprofile: str = None,
) -> Optional[str]:
    headers = {"Accept": "application/json"}
    if wikidata_user_agent_header is not None:
        headers["User-Agent"] = wikidata_user_agent_header

    if entity_type == "item":
        srnamespace = 0
        srqiprofile = "classic_noboostlinks" if srqiprofile is None else srqiprofile
    elif entity_type == "property":
        srnamespace = 120
        srqiprofile = "classic" if srqiprofile is None else srqiprofile
    else:
        raise ValueError("entity_type must be either 'property' or 'item'")

    params = {
        "action": "query",
        "list": "search",
        "srsearch": search,
        "srnamespace": srnamespace,
        "srlimit": 1,
        "srqiprofile": srqiprofile,
        "srwhat": "text",
        "format": "json",
    }

    response = requests.get(url, headers=headers, params=params)

    if response.status_code == 200:
        title = get_nested_value(response.json(), ["query", "search", 0, "title"])
        if title is None:
            return f"I couldn't find any {entity_type} for '{search}'. Please rephrase your request and try again"
        # if there is a prefix, strip it off
        return title.split(":")[-1]
    else:
        return "Sorry, I got an error. Please try again."

def run_sparql(
        query: str,
        url="https://query.wikidata.org/sparql",
        user_agent_header: str = wikidata_user_agent_header,
) -> List[Dict[str, Any]]:
    headers = {"Accept": "application/json"}
    if wikidata_user_agent_header is not None:
        headers["User-Agent"] = wikidata_user_agent_header

    response = requests.get(
        url, headers=headers, params={"query": query, "format": "json"}
    )

    if response.status_code != 200:
        return "That query failed. Perhaps you could try a different one?"
    results = get_nested_value(response.json(), ["results", "bindings"])
    return json.dumps(results)


sql_result = run_sparql("SELECT (COUNT(?children) as ?count) WHERE { wd:Q1339 wdt:P40 ?children . }")
print(sql_result)


### Agent wraps the tools
from langchain.agents import (
    Tool,
    AgentExecutor,
    LLMSingleActionAgent,
    AgentOutputParser,
)

# Define which tools the agent can use to answer user queries
tools = [
    Tool(
        name="ItemLookup",
        func=(lambda x: vocab_lookup(x, entity_type="item")),
        description="useful for when you need to know the q-number for an item",
    ),
    Tool(
        name="PropertyLookup",
        func=(lambda x: vocab_lookup(x, entity_type="property")),
        description="useful for when you need to know the p-number for a property",
    ),
    Tool(
        name="SparqlQueryRunner",
        func=run_sparql,
        description="useful for getting results from a wikibase",
    ),
]

或者传入构造的函数，比如下面传入的 multi-input，直接传入参数 String 然后分解参数。

def multiplier(a, b):
    return a * b

def parsing_multiplier(string):
    a, b = string.split(",")
    return multiplier(int(a), int(b))
llm = OpenAI(temperature=0)
tools = [
    Tool(
        name="Multiplier",
        func=parsing_multiplier,
        description="useful for when you need to multiply two numbers together. The input to this tool should be a comma separated list of numbers of length two, representing the two numbers you want to multiply together. For example, `1,2` would be the input if you wanted to multiply 1 by 2.",
    )
]

https://python.langchain.com/docs/modules/agents/tools/multi_input_tool
或者自定义类。


import yfinance as yf
from datetime import datetime, timedelta

def get_current_stock_price(ticker):
    """Method to get current stock price"""

    ticker_data = yf.Ticker(ticker)
    recent = ticker_data.history(period="1d")
    return {"price": recent.iloc[0]["Close"], "currency": ticker_data.info["currency"]}

def get_stock_performance(ticker, days):
    """Method to get stock price change in percentage"""

    past_date = datetime.today() - timedelta(days=days)
    ticker_data = yf.Ticker(ticker)
    history = ticker_data.history(start=past_date)
    old_price = history.iloc[0]["Close"]
    current_price = history.iloc[-1]["Close"]
    return {"percent_change": ((current_price - old_price) / old_price) * 100}

# res1 = get_current_stock_price("MSFT")
# print(res1)
# res2 = get_stock_performance("MSFT", 30)
# print(res2)

from typing import Type
from pydantic import BaseModel, Field
from langchain.tools import BaseTool

class CurrentStockPriceInput(BaseModel):
    """Inputs for get_current_stock_price"""

    ticker: str = Field(description="Ticker symbol of the stock")

class CurrentStockPriceTool(BaseTool):
    name = "get_current_stock_price"
    description = """
        Useful when you want to get current stock price.
        You should enter the stock ticker symbol recognized by the yahoo finance
        """
    args_schema: Type[BaseModel] = CurrentStockPriceInput

    def _run(self, ticker: str):
        price_response = get_current_stock_price(ticker)
        return price_response

    def _arun(self, ticker: str):
        raise NotImplementedError("get_current_stock_price does not support async")

class StockPercentChangeInput(BaseModel):
    """Inputs for get_stock_performance"""

    ticker: str = Field(description="Ticker symbol of the stock")
    days: int = Field(description="Timedelta days to get past date from current date")

class StockPerformanceTool(BaseTool):
    name = "get_stock_performance"
    description = """
        Useful when you want to check performance of the stock.
        You should enter the stock ticker symbol recognized by the yahoo finance.
        You should enter days as number of days from today from which performance needs to be check.
        output will be the change in the stock price represented as a percentage.
        """
    args_schema: Type[BaseModel] = StockPercentChangeInput

    def _run(self, ticker: str, days: int):
        response = get_stock_performance(ticker, days)
        return response

    def _arun(self, ticker: str):
        raise NotImplementedError("get_stock_performance does not support async")

from langchain.agents import AgentType
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent

llm = ChatOpenAI(model="gpt-3.5-turbo-0613", temperature=0)

tools = [CurrentStockPriceTool(), StockPerformanceTool()]

agent = initialize_agent(tools, llm, agent=AgentType.OPENAI_FUNCTIONS, verbose=True)

res3 = agent.run(
    "What is the current price of Microsoft stock? How it has performed over past 6 months?"
)
print(res3)

至于这里为什么 agent=AgentType.OPENAI_FUNCTIONS ？文章第二部分会提到。

1.2 搜索引擎等第三方工具

直接通过 serp 进行接口调用，可点击 https://serpapi.com/ 进行查看所有支持的接口类型，也包括百度，涉及到接口问题，需要添加 api_key。

# 需要添加 os.environ["SERPAPI_API_KEY"] = ""

# Load the tool configs that are needed.
search = SerpAPIWrapper()
llm_math_chain = LLMMathChain(llm=llm, verbose=True)
tools = [
    Tool.from_function(
        func=search.run,
        name="Search",
        description="useful for when you need to answer questions about current events"
        # coroutine= ... <- you can specify an async method if desired as well
    ),
]

也可直接使用 langchain 自带内部的接口工具。

llm = OpenAI(temperature=0)
tools = load_tools(["wikipedia", "llm-math", "terminal"], llm=llm)
agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
)



from llama_index.tools.ondemand_loader_tool import OnDemandLoaderTool
from llama_index.readers.wikipedia import WikipediaReader
from typing import List

from pydantic import BaseModel

reader = WikipediaReader()

tool = OnDemandLoaderTool.from_defaults(
    reader,
    name="Wikipedia Tool",
    description="A tool for loading and querying articles from Wikipedia",
)

# run only the llama_Index Tool by itself
tool(["Berlin"], query_str="What's the arts and culture scene in Berlin?")

# run tool from LangChain Agent
lc_tool = tool.to_langchain_structured_tool(verbose=True)
lc_tool.run(tool_input={"pages": ["Berlin"], "query_str": "What's the arts and culture scene in Berlin?"})

1.3 引入 langchain.tools 中自带 openai functions

from langchain.chat_models import ChatOpenAI
from langchain.schema import HumanMessage

model = ChatOpenAI(model="gpt-3.5-turbo-0613")

from langchain.tools import MoveFileTool, format_tool_to_openai_function

tools = [MoveFileTool()]
functions = [format_tool_to_openai_function(t) for t in tools]

message = model.predict_messages(
    [HumanMessage(content="move file foo to bar")], functions=functions
)
print(message)
print(message.additional_kwargs["function_call"])

file management

https://python.langchain.com/docs/modules/agents/tools/tools_as_openai_functions

1.4 tools 中再次包装 chains


class CalculatorInput(pydantic.BaseModel):
    question: str = pydantic.Field()

llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)

class PrimeInput(pydantic.BaseModel):
    n: int = pydantic.Field()

def get_prime(n: int, primes: dict = primes) -> str:
    return str(primes.get(int(n)))

async def aget_prime(n: int, primes: dict = primes) -> str:
    return str(primes.get(int(n)))

class CalculatorInput(pydantic.BaseModel):
    question: str = pydantic.Field()

tools = [
    Tool(
        name="GetPrime",
        func=get_prime,
        description="A tool that returns the `n`th prime number",
        args_schema=PrimeInput,
        coroutine=aget_prime,
    ),
    Tool.from_function(
        func=llm_math_chain.run,
        name="Calculator",
        description="Useful for when you need to compute mathematical expressions",
        args_schema=CalculatorInput,
        coroutine=llm_math_chain.arun,
    ),
]
agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

1.5 tool 与 vectorstores 结合

利用 embeddings 将数据存入向量数据库，然后进行检索。


from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA

llm = OpenAI(temperature=0)

from pathlib import Path
from langchain.document_loaders import TextLoader

doc_path = "E:\DEVELOP\LLM_Demo\examples\state_of_the_union.txt"

loader = TextLoader(doc_path)
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()
docsearch = Chroma.from_documents(texts, embeddings, collection_name="state-of-union")

state_of_union = RetrievalQA.from_chain_type(
    llm=llm, chain_type="stuff", retriever=docsearch.as_retriever()
)
###
from langchain.document_loaders import WebBaseLoader
loader = WebBaseLoader("https://beta.ruff.rs/docs/faq/")

docs = loader.load()
ruff_texts = text_splitter.split_documents(docs)
ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name="ruff")
ruff = RetrievalQA.from_chain_type(
    llm=llm, chain_type="stuff", retriever=ruff_db.as_retriever()
)

# Import things that are needed generically
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.tools import BaseTool
from langchain.llms import OpenAI
from langchain import LLMMathChain, SerpAPIWrapper

tools = [
    Tool(
        name="State of Union QA System",
        func=state_of_union.run,
        description="useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.",
    ),
    Tool(
        name="Ruff QA System",
        func=ruff.run,
        description="useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.",
    ),
]

# Construct the agent. We will use the default agent type here.
# See documentation for a full list of options.
agent = initialize_agent(
    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
)

res = agent.run(
    "What did biden say about ketanji brown jackson in the state of the union address?"
)

print(res)

1.6 调用浏览器工具库

如果已有库工具，可以直接将相关的工具作为 tools。


from langchain.agents import AgentType
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent

from langchain.agents.agent_toolkits import PlayWrightBrowserToolkit
from langchain.tools.playwright.utils import (
    create_async_playwright_browser,
    create_sync_playwright_browser,  # A synchronous browser is available, though it isn't compatible with jupyter.
)

async_browser = create_async_playwright_browser()
browser_toolkit = PlayWrightBrowserToolkit.from_browser(async_browser=async_browser)
tools = browser_toolkit.get_tools()

llm = ChatOpenAI(temperature=0)  # Also works well with Anthropic models
agent_chain = initialize_agent(tools, llm, agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
                               verbose=True)

response1 = agent_chain.arun(input="Hi I'm Erica.")
print(response1)

1.7 sqlite 数据库加上 chain，整体作为 tool 工具


from langchain import LLMMathChain, OpenAI, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType

llm = OpenAI(temperature=0)

search = SerpAPIWrapper()
llm_math_chain = LLMMathChain(llm=llm, verbose=True)

db = SQLDatabase.from_uri("sqlite:///../../../../../notebooks/Chinook.db")
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)

tools = [
    Tool(
        name="Search",
        func=search.run,
        description="useful for when you need to answer questions about current events. You should ask targeted questions"
    ),
    Tool(
        name="Calculator",
        func=llm_math_chain.run,
        description="useful for when you need to answer questions about math"
    ),
    Tool(
        name="FooBar DB",
        func=db_chain.run,
        description="useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context"
    )
]

mrkl = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)

1.8 StructuredTool dataclass 进行接口访问

To dynamically generate a structured tool from a given function, the fastest way to get started is with

import requests
from langchain.tools import StructuredTool


def post_message(url: str, body: dict, parameters: Optional[dict] = None) -> str:
    """Sends a POST request to the given url with the given body and parameters."""
    result = requests.post(url, json=body, params=parameters)
    return f"Status: {result.status_code} - {result.text}"


tool = StructuredTool.from_function(post_message)

1.9 decorator 作为 tool

import requests
from langchain.tools import tool


@tool
def post_message(url: str, body: dict, parameters: Optional[dict] = None) -> str:
    """Sends a POST request to the given url with the given body and parameters."""
    result = requests.post(url, json=body, params=parameters)
    return f"Status: {result.status_code} - {result.text}"

https://api.python.langchain.com/en/latest/tools/langchain.tools.base.tool.html

1.10 修改 tool 的属性

tools = load_tools(["serpapi", "llm-math"], llm=llm)

tools[0].name = "Google Search"

1.11 Defining the priorities among Tools

对所有包装的工具进行优先级定义。
When you made a Custom tool, you may want the Agent to use the custom tool more than normal tools.
For example, you made a custom tool, which gets information on music from your database. When a user wants information on songs, You want the Agent to use the custom tool more than the normal Search tool. But the Agent might prioritize a normal Search tool.
This can be accomplished by adding a statement such as Use this more than the normal search if the question is about Music, like 'who is the singer of yesterday?' or 'what is the most popular song in 2022?' to the description.
https://python.langchain.com/docs/modules/agents/tools/custom_tools

参考资料：
Introduction | 🦜️🔗 Langchain

最后编辑于 ：
©著作权归作者所有,转载或内容合作请联系作者
  • 人面猴
    序言：七十年代末，一起剥皮案震惊了整个滨河市，随后出现的几起案子，更是在滨河造成了极大的恐慌，老刑警刘岩，带你破解...
    沈念sama阅读 217,734评论 6赞 505
  • 死咒
    序言：滨河连续发生了三起死亡事件，死亡现场离奇诡异，居然都是意外死亡，警方通过查阅死者的电脑和手机，发现死者居然都...
    沈念sama阅读 92,931评论 3赞 394
  • 救了他两次的神仙让他今天三更去死
    文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
    开封第一讲书人阅读 164,133评论 0赞 354
  • 道士缉凶录：失踪的卖姜人
    文/不坏的土叔 我叫张陵，是天一观的道长。 经常有香客问我，道长，这世上最难降的妖魔是什么？ 我笑而不...
    开封第一讲书人阅读 58,532评论 1赞 293
  • 港岛之恋（遗憾婚礼）
    正文 为了忘掉前任，我火速办了婚礼，结果婚礼上，老公的妹妹穿的比我还像新娘。我一直安慰自己，他们只是感情好，可当我...
    茶点故事阅读 67,585评论 6赞 392
  • 恶毒庶女顶嫁案：这布局不是一般人想出来的
    文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
    开封第一讲书人阅读 51,462评论 1赞 302
  • 城市分裂传说
    那天，我揣着相机与录音，去河边找鬼。 笑死，一个胖子当着我的面吹牛，可吹牛的内容都是我干的。 我是一名探鬼主播，决...
    沈念sama阅读 40,262评论 3赞 418
  • 双鸳鸯连环套：你想象不到人心有多黑
    文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
    开封第一讲书人阅读 39,153评论 0赞 276
  • 万荣杀人案实录
    序言：老挝万荣一对情侣失踪，失踪者是张志新（化名）和其女友刘颖，没想到半个月后，有当地人在树林里发现了一具尸体，经...
    沈念sama阅读 45,587评论 1赞 314
  • 护林员之死
    正文 独居荒郊野岭守林人离奇死亡，尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 37,792评论 3赞 336
  • 白月光启示录
    正文 我和宋清朗相恋三年，在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 39,919评论 1赞 348
  • 活死人
    序言：一个原本活蹦乱跳的男人离奇死亡，死状恐怖，灵堂内的尸体忽然破棺而出，到底是诈尸还是另有隐情，我是刑警宁泽，带...
    沈念sama阅读 35,635评论 5赞 345
  • 日本核电站爆炸内幕
    正文 年R本政府宣布，位于F岛的核电站，受9级特大地震影响，放射性物质发生泄漏。R本人自食恶果不足惜，却给世界环境...
    茶点故事阅读 41,237评论 3赞 329
  • 男人毒药：我在死后第九天来索命
    文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹，春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 31,855评论 0赞 22
  • 一桩弑父案，背后竟有这般阴谋
    文/苍兰香墨 我抬头看了看天上的太阳。三九已至，却和暖如春，着一层夹袄步出监牢的瞬间，已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 32,983评论 1赞 269
  • 情欲美人皮
    我被黑心中介骗来泰国打工， 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留，地道东北人。 一个月前我还...
    沈念sama阅读 48,048评论 3赞 370
  • 代替公主和亲
    正文 我出身青楼，却偏偏与公主长得像，于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子，可洞房花烛夜当晚...
    茶点故事阅读 44,864评论 2赞 354

推荐阅读更多精彩内容